#20955
Title:
Predicting Myocardial rupture after acute myocardial infarction in hospitalized patients using machine learning
There is below links to the dataset and discription of it:
We can do it today.
Dataset(.csv):
https://leicester.figshare.com/ndownloader/files/23581310
Dataset discription:
https://leicester.figshare.com/articles/dataset/Myocardial_infarction_complications_Database/12045261?file=22803572
Descriptive statistics:
https://leicester.figshare.com/articles/dataset/Myocardial_infarction_complications_Database/12045261?file=22803695
Then we need to apply the following classification models for classification :
SVM
Naive Bayes
Logistic Regression
Decision Tree
Random Forest
LightGBM
XGboost
to predict Myocardial rupture complication after acute myocardial infarction for the time of admission to hospital. This can be done according to the discription of the dataset using all input columns (2-112) except 93, 94, 95, 100, 101, 102, 103, 104, 105can be usedfor prediction.
Then we need to write 3000 words using the attached word format to explain this work which include the following sections:
Abstract
Introduction
Related work
Materials and methods:
-Description of the Data
-Data preprocessing and cleaning
Model development
Result
Discussion
conclusion
References
OTHER: Reviewers Notes: . Although this paper holds some values, however, the author did not provide enough literature review. There are a lot of researches regarding such issue and they are worth to be explained and compared with such a paper. For instance, the author might look at the following article and notice the conclusion of such a paper. Wu, Jinlin, et al. “Predicting in-hospital rupture of type A aortic dissection using Random Forest.” Journal of thoracic disease 11.11 (2019): 4634. • I recommend the author explain the used model mathematically, graphically, or flowchart. • The author should provide technical analysis and compare the result with other methods if any. • The quality of figures is deficient and cannot be accepted. I recommend accepting this paper after possible reconstruction.
